scholarly journals Joint multi-domain feature learning for image steganalysis based on CNN

2020 ◽  
Author(s):  
Ze Wang ◽  
Mingzhi Chen ◽  
Yu Yang ◽  
Min Lei ◽  
Zhexuan Dong
Keyword(s):  
Feature Learning ◽  
Learning Ability ◽  
Detection Accuracy ◽  
Model Learning ◽  
Image Steganalysis ◽  
Detection Mechanism ◽  
Nonlinear Detection ◽  
High Pass ◽  
Embedding Rate ◽  
Image Datasets

Abstract Recently steganalysis methods based on convolutional neural networks (CNN) have achieved great improvement. However, detection against adaptive steganographic algorithms with low embedding rates has still been a challenging task. To deal with this problem, we propose a CNN steganalysis model employing the joint domain detection mechanism and nonlinear detection mechanism. For the joint domain detection mechanism, we use not only the high-pass filters from the SRM for spatial residuals, but also the patterns from the DCTR for frequency steganographic impacts. For the nonlinear detection mechanism, we enlarge steganographic effects by nonlinearly transforming the extracted steganographic residual information. In addition, we innovatively put forward a model learning method based on the high learning ability of a model. That is, we use lower embedding rate image datasets to train a model and higher embedding rate image datasets to test the model, which effectively improves sensitivity to steganographic traces. Compared with the existing steganalysis models such as SRM+EC, Ye-Net, Xu-Net, Yedroudj-Net and Zhu-Net, the detection accuracy of our model is about 4%∼6% higher than that of the best Zhu-Net model.

scholarly journals Wheel fault diagnosis model based on multichannel attention and supervised contrastive learning

2021 ◽  
Vol 13 (12) ◽  
pp. 168781402110670
Author(s):  
Yanxiang Chen ◽  
Zuxing Zhao ◽  
Euiyoul Kim ◽  
Haiyang Liu ◽  
Juan Xu ◽  
...  
Keyword(s):  
Network Architecture ◽  
Feature Learning ◽  
Feature Representation ◽  
Diagnostic Methods ◽  
Learning Ability ◽  
Noise Interference ◽  
Backbone Network ◽  
Mechanical Methods ◽  
Wheel Flat ◽  
Wheel Radius

As wheels are important components of train operation, diagnosing and predicting wheel faults are essential to ensure the reliability of rail transit. Currently, the existing studies always separately deal with two main types of wheel faults, namely wheel radius difference and wheel flat, even though they are both reflected by wheel radius changes. Moreover, traditional diagnostic methods, such as mechanical methods or a combination of data analysis methods, have limited abilities to efficiently extract data features. Deep learning models have become useful tools to automatically learn features from raw vibration signals. However, research on improving the feature-learning capabilities of models under noise interference to yield higher wheel diagnostic accuracies has not yet been conducted. In this paper, a unified training framework with the same model architecture and loss function is established for two homologous wheel faults. After selecting deep residual networks (ResNets) as the backbone network to build the model, we add the squeeze and excitation (SE) module based on a multichannel attention mechanism to the backbone network to learn the global relationships among feature channels. Then the influence of noise interference features is reduced while the extraction of useful information features is enhanced, leading to the improved feature-learning ability of ResNet. To further obtain effective feature representation using the model, we introduce supervised contrastive loss (SCL) on the basis of ResNet + SE to enlarge the feature distances of different fault classes through a comparison between positive and negative examples under label supervision to obtain a better class differentiation and higher diagnostic accuracy. We also complete a regression task to predict the fault degrees of wheel radius difference and wheel flat without changing the network architecture. The extensive experimental results show that the proposed model has a high accuracy in diagnosing and predicting two types of wheel faults.

Deep learning for extracting water body from Sentinel-2 MSI imagery

2021 ◽  
Author(s):  
Shuren Chou
Keyword(s):  
Deep Learning ◽  
Distance Measure ◽  
Accuracy Assessment ◽  
Feature Learning ◽  
Search Space ◽  
Water Bodies ◽  
Detection Accuracy ◽  
Simple Linear Iterative Clustering ◽  
Clustering Center ◽  
Sentinel 2

<p>Deep learning has a good capacity of hierarchical feature learning from unlabeled remote sensing images. In this study, the simple linear iterative clustering (SLIC) method was improved to segment the image into good quality super-pixels. Then, we used the convolutional neural network (CNN) to extract of water bodies from Sentinel-2 MSI data using deep learning technique. In the proposed framework, the improved SLIC method obtained the correct water bodies boundary by optimizing the initial clustering center, designing a dynamic distance measure, and expanding the search space. In addition, it is different from traditional extraction of water bodies methods that cannot achieve multi-level water bodies detection. Experimental results showed that this method had higher detection accuracy and robustness than other methods. This study was able to extract water bodies from remotely sensed images with deep learning and to conduct accuracy assessment.</p>

scholarly journals Change Detection Based on Multi-Grained Cascade Forest and Multi-Scale Fusion for SAR Images

2019 ◽  
Vol 11 (2) ◽  
pp. 142 ◽  
Author(s):  
Wenping Ma ◽  
Hui Yang ◽  
Yue Wu ◽  
Yunta Xiong ◽  
Tao Hu ◽  
...  
Keyword(s):  
Change Detection ◽  
Representation Learning ◽  
Local Information ◽  
Learning Ability ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Image Block ◽  
Sar Images ◽  
Difference Image ◽  
Multi Scale

In this paper, a novel change detection approach based on multi-grained cascade forest(gcForest) and multi-scale fusion for synthetic aperture radar (SAR) images is proposed. It detectsthe changed and unchanged areas of the images by using the well-trained gcForest. Most existingchange detection methods need to select the appropriate size of the image block. However, thesingle size image block only provides a part of the local information, and gcForest cannot achieve agood effect on the image representation learning ability. Therefore, the proposed approach choosesdifferent sizes of image blocks as the input of gcForest, which can learn more image characteristicsand reduce the influence of the local information of the image on the classification result as well.In addition, in order to improve the detection accuracy of those pixels whose gray value changesabruptly, the proposed approach combines gradient information of the difference image with theprobability map obtained from the well-trained gcForest. Therefore, the image edge information canbe enhanced and the accuracy of edge detection can be improved by extracting the image gradientinformation. Experiments on four data sets indicate that the proposed approach outperforms otherstate-of-the-art algorithms.

scholarly journals Nonlinear Manifold Learning Integrated with Fully Convolutional Networks for PolSAR Image Classification

2020 ◽  
Vol 12 (4) ◽  
pp. 655
Author(s):  
Chu He ◽  
Mingxia Tu ◽  
Dehui Xiong ◽  
Mingsheng Liao
Keyword(s):  
Image Classification ◽  
Manifold Learning ◽  
Feature Learning ◽  
Learning Ability ◽  
High Dimensional ◽  
Compact Representation ◽  
Deep Network ◽  
Convolutional Networks ◽  
Fully Convolutional Networks ◽  
Spatial Features

Synthetic Aperture Rradar (SAR) provides rich ground information for remote sensing survey and can be used all time and in all weather conditions. Polarimetric SAR (PolSAR) can further reveal surface scattering difference and improve radar’s application ability. Most existing classification methods for PolSAR imagery are based on manual features, such methods with fixed pattern has poor data adaptability and low feature utilization, if directly input to the classifier. Therefore, combining PolSAR data characteristics and deep network with auto-feature learning ability forms a new breakthrough direction. In fact, feature learning of deep network is to realize function approximation from data to label, through multi-layer accumulation, but finite layers limit the network’s mapping ability. According to manifold hypothesis, high-dimensional data exists in potential low-dimensional manifold and different types of data locates in different manifolds. Manifold learning can model core variables of the target, and separate different data’s manifold as much as possible, so as to complete data classification better. Therefore, taking manifold hypothesis as a starting point, nonlinear manifold learning integrated with fully convolutional networks for PolSAR image classification method is proposed in this paper. Firstly, high-dimensional polarized features are extracted based on scattering matrix and coherence matrix of original PolSAR data, whose compact representation is mined by manifold learning. Meanwhile, drawing on transfer learning, pre-trained Fully Convolutional Networks (FCN) model is utilized to learn deep spatial features of PolSAR imagery. Considering complementary advantages, weighted strategy is adopted to embed manifold representation into deep spatial features, which are input into support vector machine (SVM) classifier for final classification. A series of experiments on three PolSAR datasets have verified effectiveness and superiority of the proposed classification algorithm.

scholarly journals Sequential Network with Residual Neural Network for Rotatory Machine Remaining Useful Life Prediction Using Deep Transfer Learning

2020 ◽  
Vol 2020 ◽  
pp. 1-16
Author(s):  
Hao Zhang ◽  
Qiang Zhang ◽  
Siyu Shao ◽  
Tianlin Niu ◽  
Xinyu Yang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Life Prediction ◽  
Feature Learning ◽  
High Accuracy ◽  
Remaining Useful Life ◽  
Learning Ability ◽  
Model Parameters ◽  
Deep Model ◽  
Useful Life

Deep learning has a strong feature learning ability, which has proved its effectiveness in fault prediction and remaining useful life prediction of rotatory machine. However, training a deep network from scratch requires a large amount of training data and is time-consuming. In the practical model training process, it is difficult for the deep model to converge when the parameter initialization is inappropriate, which results in poor prediction performance. In this paper, a novel deep learning framework is proposed to predict the remaining useful life of rotatory machine with high accuracy. Firstly, model parameters and feature learning ability of the pretrained model are transferred to the new network by means of transfer learning to achieve reasonable initialization. Then, the specific sensor signals are converted to RGB image as the specific task data to fine-tune the parameters of the high-level network structure. The features extracted from the pretrained network are the input into the Bidirectional Long Short-Term Memory to obtain the RUL prediction results. The ability of LSTM to model sequence signals and the dynamic learning ability of bidirectional propagation to time information contribute to accurate RUL prediction. Finally, the deep model proposed in this paper is tested on the sensor signal dataset of bearing and gearbox. The high accuracy prediction results show the superiority of the transfer learning-based sequential network in RUL prediction.

scholarly journals A Novel Deep Feature Learning Method Based on the Fused-Stacked AEs for Planetary Gear Fault Diagnosis

Energies ◽  
2019 ◽  
Vol 12 (23) ◽  
pp. 4522
Author(s):  
Xihui Chen ◽  
Aimin Ji ◽  
Gang Cheng
Keyword(s):  
Deep Learning ◽  
Fault Diagnosis ◽  
Feature Learning ◽  
Planetary Gear ◽  
Learning Ability ◽  
Energy Industry ◽  
Deep Feature ◽  
Gear Fault ◽  
Deep Feature Learning ◽  
Electromechanical Equipment

Planetary gear is the key component of the transmission system of electromechanical equipment for energy industry, and it is easy to damage, which affects the reliability and operation efficiency of electromechanical equipment of energy industry. Therefore, it is of great significance to extract the useful fault features and diagnose faults based on raw vibration signals. In this paper, a novel deep feature learning method based on the fused-stacked autoencoders (AEs) for planetary gear fault diagnosis was proposed. First, to improve the data learning ability and the robustness of feature extraction process of AE model, the sparse autoencoder (SAE) and the contractive autoencoder (CAE) were studied, respectively. Then, the quantum ant colony algorithm (QACA) was used to optimize the specific location and key parameters of SAEs and CAEs in deep learning architecture, and multiple SAEs and multiple CAEs were stacked alternately to form a novel deep learning architecture, which gave the deep learning architecture better data learning ability and robustness of feature extraction. The experimental results show that the proposed method can address the raw vibration signals of planetary gear. Compared with other deep learning architectures and shallow learning architecture, the proposed method has better diagnosis performance, and it is an effective method of deep feature learning and fault diagnosis.

scholarly journals A Novel Cuckoo Search Optimized Deep Auto-Encoder Network-Based Fault Diagnosis Method for Rolling Bearing

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Jinyu Tong ◽  
Jin Luo ◽  
Haiyang Pan ◽  
Jinde Zheng ◽  
Qing Zhang
Keyword(s):  
Fault Diagnosis ◽  
Working Conditions ◽  
Search Algorithm ◽  
Feature Learning ◽  
Cuckoo Search ◽  
Rolling Bearing ◽  
Cuckoo Search Algorithm ◽  
Learning Ability ◽  
Penalty Term ◽  
Experimental Data Analysis

To enhance the performance of deep auto-encoder (AE) under complex working conditions, a novel deep auto-encoder network method for rolling bearing fault diagnosis is proposed in this paper. First, multiscale analysis is adopted to extract the multiscale features from the raw vibration signals of rolling bearing. Second, the sparse penalty term and contractive penalty term are used simultaneously to regularize the loss function of auto-encoder to enhance the feature learning ability of networks. Finally, the cuckoo search algorithm (CS) is used to find the optimal hyperparameters automatically. The proposed method is applied to the experimental data analysis. The results indicate that the proposed method could more effectively distinguish fault categories and severities of rolling bearings under different working conditions than other methods.

scholarly journals A knowledge-guided and manual intervention-based gene expression programming for PM2.5 concentration prediction

2021 ◽  
Vol 269 ◽  
pp. 01011
Author(s):  
Chaoxue Wang ◽  
Xiaoli Jia ◽  
Fan Zhang ◽  
Yuhang Pan
Keyword(s):  
Neural Network ◽  
Gene Expression ◽  
Influencing Factors ◽  
Gene Expression Programming ◽  
Learning Ability ◽  
Back Propagation Algorithm ◽  
Model Learning ◽  
Manual Intervention ◽  
Concentration Prediction ◽  
Pm2.5 Concentration

In view of the lack of interpretation and inability to know the occurrence mechanism of PM2.5 concentration by deep learning algorithm in solving PM2.5 concentration prediction problem, this paper adopts a knowledge-guided and manual intervention-based gene expression programming (KMGEP) to solve it. The KMGEP algorithm not only has strong model learning ability, but also can obtain the explicit function relationship between PM2.5 concentration and its influencing factors. In the process of algorithm implementation, knowledge guidance and manual intervention are introduced to GEP for predicting PM2.5 concentration so as to improve its global optimization ability and convergence speed. In this paper, the daily PM2.5 concentration prediction in winter (from December to February) in Xi’an region is taken as an example, and the KMGEP algorithm is compared with the artificial neural network back propagation algorithm (BP-ANN) and the convolutional neural network and long short-term memory neural network combined model (CNN-LSTM). Experimental results show that the KMGEP algorithm not only has high prediction accuracy in solving the PM2.5 concentration prediction, but also the obtained function expression can reveal the occurrence relationship between PM2.5 concentration and its influencing factors.

scholarly journals Detection of Stego Images with Adaptively Embedded Data by Component Analysis Methods

2021 ◽  
Vol 6 (2) ◽  
pp. 146-154
Author(s):  
Dmytro Progonov ◽  
Keyword(s):  
Communication Systems ◽  
Principal Component ◽  
Component Analysis ◽  
Detection Accuracy ◽  
Sensitive Data ◽  
Analysis Methods ◽  
Cover Ratio ◽  
High Pass ◽  
Selection Of ◽  
Image Calibration

Ensuring the effective protection of personal and corporate sensitive data is topical task today. The special interest is taken at sensitive data leakage prevention during files transmission in communication systems. In most cases, these leakages are conducted by usage of advance adaptive steganographic methods. These methods are aimed at minimizing distortions of cover files, such as digital images, during data hiding that negatively impact on detection accuracy of formed stego images. For overcoming this shortcoming, it was proposed to pre-process (calibrate) analyzed images for increasing stego- to-cover ratio. The modern paradigm of image calibration is based on usage of enormous set of high-pass filters. However, selection of filter(s) that maximizes the probability of stego images detection is non-trivial task, especially in case of limited a prior knowledge about embedding methods. For solving this task, we proposed to use component analysis methods for image calibration, namely principal components analysis. Results of comparative analysis of novel maxSRMd2 cover rich model and proposed solution showed that principal component analysis allows increasing detection accuracy up to 1.5% even in the most difficult cases (low cover image payload and absence of cover- stego images pairs in training set).

scholarly journals Breast Cancer Detection and Diagnosis Using Mammographic Data: Systematic Review

10.2196/14464 ◽  
2019 ◽  
Vol 21 (7) ◽  
pp. e14464 ◽  
Author(s):  
Syed Jamal Safdar Gardezi ◽  
Ahmed Elazab ◽  
Baiying Lei ◽  
Tianfu Wang
Keyword(s):  
Breast Cancer ◽  
Cancer Diagnosis ◽  
Data Augmentation ◽  
Computational Cost ◽  
Feature Learning ◽  
Breast Cancer Diagnosis ◽  
Clinical Analysis ◽  
Learning Ability ◽  
Cad Systems ◽  
Imaging Research

Background Machine learning (ML) has become a vital part of medical imaging research. ML methods have evolved over the years from manual seeded inputs to automatic initializations. The advancements in the field of ML have led to more intelligent and self-reliant computer-aided diagnosis (CAD) systems, as the learning ability of ML methods has been constantly improving. More and more automated methods are emerging with deep feature learning and representations. Recent advancements of ML with deeper and extensive representation approaches, commonly known as deep learning (DL) approaches, have made a very significant impact on improving the diagnostics capabilities of the CAD systems. Objective This review aimed to survey both traditional ML and DL literature with particular application for breast cancer diagnosis. The review also provided a brief insight into some well-known DL networks. Methods In this paper, we present an overview of ML and DL techniques with particular application for breast cancer. Specifically, we search the PubMed, Google Scholar, MEDLINE, ScienceDirect, Springer, and Web of Science databases and retrieve the studies in DL for the past 5 years that have used multiview mammogram datasets. Results The analysis of traditional ML reveals the limited usage of the methods, whereas the DL methods have great potential for implementation in clinical analysis and improve the diagnostic capability of existing CAD systems. Conclusions From the literature, it can be found that heterogeneous breast densities make masses more challenging to detect and classify compared with calcifications. The traditional ML methods present confined approaches limited to either particular density type or datasets. Although the DL methods show promising improvements in breast cancer diagnosis, there are still issues of data scarcity and computational cost, which have been overcome to a significant extent by applying data augmentation and improved computational power of DL algorithms.

Sign in / Sign up

Export Citation Format

Share Document